3D-ADAM: A Dataset for 3D Anomaly Detection in Additive Manufacturing

TL;DR

The paper introduces 3D-ADAM, a comprehensive large-scale dataset of 3D surface defect scans in additive manufacturing, designed to improve anomaly detection methods in real industrial settings.

Contribution

It provides the first extensive, industry-relevant 3D defect dataset for additive manufacturing, including diverse real-world conditions and detailed annotations.

Findings

State-of-the-art models struggle with 3D-ADAM's complexity.

The dataset reflects real manufacturing variability.

Expert validation confirms industrial relevance.

Abstract

Surface defects are a primary source of yield loss in manufacturing, yet existing anomaly detection methods often fail in real-world deployment due to limited and unrepresentative datasets. To overcome this, we introduce 3D-ADAM, a 3D Anomaly Detection in Additive Manufacturing dataset, that is the first large-scale, industry-relevant dataset for RGB+3D surface defect detection in additive manufacturing. 3D-ADAM comprises 14,120 high-resolution scans of 217 unique parts, captured with four industrial depth sensors, and includes 27,346 annotated defects across 12 categories along with 27,346 annotations of machine element features in 16 classes. 3D-ADAM is captured in a real industrial environment and as such reflects real production conditions, including variations in part placement, sensor positioning, lighting, and partial occlusion. Benchmarking state-of-the-art models demonstrates that 3D-ADAM presents substantial challenges beyond existing datasets. Validation through expert labelling surveys with industry partners further confirms its industrial relevance. By providing this benchmark, 3D-ADAM establishes a foundation for advancing robust 3D anomaly detection capable of meeting manufacturing demands.